A High Precision Recommendation Algorithm Based on Combination Features

Conventional recommendation systems often use binary relations matrices, which could not represent raw data sets efficiently and uniformly. The graph model can represent multiple relationships and form a unified standard of the feature space to recommend the candidate items. Existing graph-based work is generally based on the path to establish the feature space of the data, only concerned about the impact of an item on the description of the user. Utilizing combination features to construct user profiles, this paper concentrates on the contribution maked by combination of items and designs a user-based collaborative filtering algorithm (CFC), and validates the validity of the algorithm in the prototype of the proposed system. The experimental results show that the recommendation algorithms can significantly improve accuracy of the recommendation.

[1]  Byeong Man Kim,et al.  Constructing User Profiles for Collaborative Recommender System , 2004, APWeb.

[2]  Sangkeun Lee,et al.  PathRank: a novel node ranking measure on a heterogeneous graph for recommender systems , 2012, CIKM.

[3]  Jun Wang,et al.  Unifying user-based and item-based collaborative filtering approaches by similarity fusion , 2006, SIGIR.

[4]  Hsinchun Chen,et al.  A graph-based recommender system for digital library , 2002, JCDL '02.

[5]  Domonkos Tikk,et al.  Scalable Collaborative Filtering Approaches for Large Recommender Systems , 2009, J. Mach. Learn. Res..

[6]  Dan Frankowski,et al.  Collaborative Filtering Recommender Systems , 2007, The Adaptive Web.

[7]  Ni Lao,et al.  Relational retrieval using a combination of path-constrained random walks , 2010, Machine Learning.

[8]  Bela Gipp,et al.  Research-paper recommender systems: a literature survey , 2015, International Journal on Digital Libraries.

[9]  Roberto Turrin,et al.  Performance of recommender algorithms on top-n recommendation tasks , 2010, RecSys '10.

[10]  Paolo Tomeo,et al.  A SPRank : Semantic Path-based Ranking for Top-N Recommendations using Linked Open Data , 2016 .

[11]  Yizhou Sun,et al.  Personalized entity recommendation: a heterogeneous information network approach , 2014, WSDM.

[12]  Yixin Chen,et al.  A comparison of a graph database and a relational database: a data provenance perspective , 2010, ACM SE '10.

[13]  Md. Saiful Islam,et al.  Efficient Answering of Why-Not Questions in Similar Graph Matching , 2015, IEEE Trans. Knowl. Data Eng..

[14]  Chunming Hu,et al.  Big graph search: challenges and techniques , 2015, Frontiers of Computer Science.

[15]  Huy Nguyen,et al.  A Modified Regularized Non-Negative Matrix Factorization for MovieLens , 2012, 2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future.

[16]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.